Frontier models ranked by benchmark intelligence — reasoning, coding, math and knowledge evals — with real-world request volume shown alongside. Sort by quality to find the strongest model, or by requests to see what the market actually runs.
| # | Model | Provider | Intelligence | Coding | Requests | Share |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 anthropic/claude-fable-5.1 | Anthropic | 53.4 | 81.6 | — | — |
| 2 | Claude Opus 5 anthropic/claude-opus-5 | Anthropic | 50.7 | 78.0 | — | — |
| 3 | Claude Fable 5 anthropic/claude-fable-5 | Anthropic | 49.7 | 76.5 | 242 | 0% |
| 4 | GPT-5.6 Sol openai/gpt-5.6-sol | OpenAI | 47.1 | 77.4 | — | — |
| 5 | Glm-5.3 zai-org/glm-5.3 | Zai-org | 44.9 | 74.8 | — | — |
| 6 | Grok 4.6 xai/grok-4.6 | xAI | 44.4 | 76.8 | — | — |
| 7 | Kimi K3 moonshot/kimi-k3 | Moonshot | 43.8 | 76.2 | — | — |
| 8 | GPT-5.6 Terra openai/gpt-5.6-terra | OpenAI | 42.3 | 76.7 | — | — |
| 9 | Claude Opus 4.8 anthropic/claude-opus-4.8 | Anthropic | 42.0 | 74.3 | 37 | 0% |
| 10 | Glm-5.3-Flash zai-org/glm-5.3-flash | Zai-org | 41.9 | 71.5 | — | — |
| 11 | Gemini 3.8 Flash google/gemini-3.8-flash | 41.2 | 76.3 | — | — | |
| 12 | Claude Opus 4.7 anthropic/claude-opus-4.7 | Anthropic | 40.7 | 73.6 | 1 | 0% |
| 13 | Qwen3.8 Max alibaba/qwen3.8-max | Alibaba | 40.3 | 71.8 | — | — |
| 14 | Gemini 3.7 Flash google/gemini-3.7-flash | 39.6 | 71.5 | — | — | |
| 15 | Grok 4.5 xai/grok-4.5 | xAI | 39.1 | 72.4 | — | — |
| 16 | GPT-5.4 openai/gpt-5.4 | OpenAI | 39.0 | 71.1 | 19.2K | 1.7% |
| 17 | GPT-5.5 openai/gpt-5.5 | OpenAI | 38.6 | 74.9 | 35.2K | 3.1% |
| 18 | GLM-5.2 zai-org/glm-5.2 | Zai-org | 38.6 | 68.8 | 16.1K | 1.4% |
| 19 | Claude Sonnet 5 anthropic/claude-sonnet-5 | Anthropic | 38.4 | 71.5 | — | — |
| 20 | GPT-5.6 Luna openai/gpt-5.6-luna | OpenAI | 37.5 | 71.4 | — | — |
| 21 | DeepSeek V4 Pro deepseek/deepseek-v4-pro | Deepseek | 36.3 | 68.8 | 57.9K | 5% |
| 22 | Gemini 3.6 Flash google/gemini-3.6-flash | 34.3 | 69.2 | — | — | |
| 23 | Qwen3.8-27b qwen/qwen3.8-27b | Alibaba Qwen | 33.9 | 68.1 | — | — |
| 24 | Gemini 3.5 Flash google/gemini-3.5-flash | 33.6 | — | — | — | |
| 25 | Claude Opus 4.6 anthropic/claude-opus-4.6 | Anthropic | 31.9 | — | — | — |
| 26 | Kimi-K2.6 moonshot/kimi-k2.6 | Moonshot | 31.3 | 61.8 | 9.4K | 0.8% |
| 27 | Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | Anthropic | 30.5 | 63.0 | — | — |
| 28 | Gemini 3.1 Pro google/gemini-3.1-pro | 30.4 | 68.8 | 40.7K | 3.5% | |
| 29 | Qwen3.7 Max alibaba/qwen3.7-max | Alibaba | 29.9 | 66.0 | — | — |
| 30 | MiniMax M3 minimax/m3 | MiniMax | 29.6 | 58.6 | — | — |
| 31 | Claude Opus 4.5 anthropic/claude-opus-4.5 | Anthropic | 29.1 | — | 1 | 0% |
| 32 | Gemini 3 Flash google/gemini-3-flash | 26.3 | — | 248.8K | 21.6% | |
| 33 | Kimi-K2.7-Code moonshot/kimi-k2.7-code | Moonshot | 26.3 | 60.8 | 4.3K | 0.4% |
| 34 | Qwen3.7 Plus alibaba/qwen3.7-plus | Alibaba | 25.8 | 55.9 | — | — |
| 35 | Grok 4.3 xai/grok-4.3 | xAI | 25.4 | 42.2 | 34.4K | 3% |
| 36 | Grok 4.20 Non-Reasoning xai/grok-4.20-0309-non-reasoning | xAI | 25.2 | — | — | — |
| 37 | Grok 4.20 Reasoning xai/grok-4.20-0309-reasoning | xAI | 25.2 | — | — | — |
| 38 | GPT-5.1 openai/gpt-5.1 | OpenAI | 24.7 | 49.4 | — | — |
| 39 | GPT-5.4 Mini openai/gpt-5.4-mini | OpenAI | 24.6 | 56.1 | 60.6K | 5.3% |
| 40 | MiniMax M2.7 minimax/m2.7 | MiniMax | 23.2 | 52.6 | — | — |
| Provider | Models | Requests |
|---|---|---|
| 13 | 766.6K | |
| OpenAI | 27 | 246.4K |
| Deepseek | 2 | 57.9K |
| xAI | 6 | 35.0K |
| Zai-org | 4 | 16.1K |
| Moonshot | 3 | 13.6K |
| Anthropic | 12 | 3.7K |
| Mistral | 1 | 2.6K |
| Ibm-granite | 1 | 2.4K |
| Meta | 5 | 1.7K |
| Black Forest Labs | 9 | 1.1K |
| Inworld | 2 | 947 |
Intelligence and coding scores come from Artificial Analysis evals baked into the catalog on every release; request volume is real aggregate demand across the open model ecosystem, refreshed daily. For the full benchmark + pricing table, see the model leaderboard.